Hadoop Mapreduce Mapper和Reducer源码

关键是里面run，setup，cleanup函数的作用！

Mapper

public class Mapper<KEYIN, VALUEIN, KEYOUT, VALUEOUT> {

  /**
   * The <code>Context</code> passed on to the {@link Mapper} implementations.
   */
  public abstract class Context
    implements MapContext<KEYIN,VALUEIN,KEYOUT,VALUEOUT> {
  }
  
  /**
   * Called once at the beginning of the task.
   */
  protected void setup(Context context
                       ) throws IOException, InterruptedException {
    // NOTHING
  }

  /**
   * Called once for each key/value pair in the input split. Most applications
   * should override this, but the default is the identity function.
   */
  @SuppressWarnings("unchecked")
  protected void map(KEYIN key, VALUEIN value, 
                     Context context) throws IOException, InterruptedException {
    context.write((KEYOUT) key, (VALUEOUT) value);
  }

  /**
   * Called once at the end of the task.
   */
  protected void cleanup(Context context
                         ) throws IOException, InterruptedException {
    // NOTHING
  }
  
  /**
   * Expert users can override this method for more complete control over the
   * execution of the Mapper.
   * @param context
   * @throws IOException
   */
  public void run(Context context) throws IOException, InterruptedException {
    setup(context);
    try {
      while (context.nextKeyValue()) {
        map(context.getCurrentKey(), context.getCurrentValue(), context);
      }
    } finally {
      cleanup(context);
    }
  }
}

public class Reducer<KEYIN,VALUEIN,KEYOUT,VALUEOUT> {

  /**
   * The <code>Context</code> passed on to the {@link Reducer} implementations.
   */
  public abstract class Context 
    implements ReduceContext<KEYIN,VALUEIN,KEYOUT,VALUEOUT> {
  }

  /**
   * Called once at the start of the task.
   */
  protected void setup(Context context
                       ) throws IOException, InterruptedException {
    // NOTHING
  }

  /**
   * This method is called once for each key. Most applications will define
   * their reduce class by overriding this method. The default implementation
   * is an identity function.
   */
  @SuppressWarnings("unchecked")
  protected void reduce(KEYIN key, Iterable<VALUEIN> values, Context context
                        ) throws IOException, InterruptedException {
    for(VALUEIN value: values) {
      context.write((KEYOUT) key, (VALUEOUT) value);
    }
  }

  /**
   * Called once at the end of the task.
   */
  protected void cleanup(Context context
                         ) throws IOException, InterruptedException {
    // NOTHING
  }

  /**
   * Advanced application writers can use the 
   * {@link #run(org.apache.hadoop.mapreduce.Reducer.Context)} method to
   * control how the reduce task works.
   */
  public void run(Context context) throws IOException, InterruptedException {
    setup(context);
    try {
      while (context.nextKey()) {
        reduce(context.getCurrentKey(), context.getValues(), context);
        // If a back up store is used, reset it
        Iterator<VALUEIN> iter = context.getValues().iterator();
        if(iter instanceof ReduceContext.ValueIterator) {
          ((ReduceContext.ValueIterator<VALUEIN>)iter).resetBackupStore();        
        }
      }
    } finally {
      cleanup(context);
    }
  }
}